review

review is a skill for Claude Code from helderberto/agent-skills. It costs 117 tokens per session (1,909 once invoked), scanned A, original, MIT.

A full review workflow for proposed code changes. It sends the changes to several independent reviewers, including checks for areas such as accessibility, security, performance, dependencies, and architecture.

In plain words
What is it for?
Use it for a complete pre-release review, validating a pull request, or getting several independent perspectives on a code change.
Why use it?
It brings different kinds of review together and ranks the findings by severity, making it easier to spot important problems before shipping.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents.

Part of the hb plugin — 40 skills, 6 agents shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/helderberto/agent-skills/review
Any agent
npx skills add helderberto/agent-skills --skill review
Clone the repo
git clone --depth 1 https://github.com/helderberto/agent-skills

Made for: Claude Code.

Or install hb, the plugin that ships this one along with the rest of its 40 skills, 6 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for review

README.md
[![agentmods](https://agentmods.dev/badge/skills/helderberto/agent-skills/review.svg)](https://agentmods.dev/skills/helderberto/agent-skills/review)
Your own site
<a href="https://agentmods.dev/skills/helderberto/agent-skills/review"><img src="https://agentmods.dev/badge/skills/helderberto/agent-skills/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,909 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00117 $0.01909
Opus 5 $0.00059 $0.00955
Sonnet 5 $0.00023 $0.00382
Haiku 4.5 $0.00012 $0.00191

Measured 6d ago against content hash 024161ccc31b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/review/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Phase

Workflow orchestrator for the REVIEW phase of the SDLC. Resolve the diff, fan out parallel read-only reviewers — each in its own subagent (fresh context) — and consolidate everything into one severity-ranked verdict.

Reviewers come from two complementary sources; use whichever fit the change (usually both):

  • Audit skills — deterministic by file type in the diff: a11y-audit, i18n, perf-audit, deps-audit, harden, safe-repo. Which run is decided by scope detection.
  • Agent lenses — independent perspectives on the whole diff: correctness, test effectiveness, security, type safety, architecture friction.

Fanning out to subagents keeps each reviewer's work out of the main thread (no bleed between a11y and security reasoning) and runs them concurrently instead of one-after-another. Findings two reviewers reach independently are the highest signal — surface that convergence.

Sibling skills: code-review is a single in-thread lens; triage-review evaluates existing reviewer comments rather than generating new ones.

Workflow

Phase 1 — Resolve the diff

Priority order:

  1. PR number passed → gh pr view <num> for context, gh pr diff <num> for the diff.
  2. Branch name passed → git diff <base>...<branch>.
  3. Nothing passed → git merge-base HEAD main (fall back master, then origin/HEAD), then git diff <base>...HEAD.

Capture the changed-file list. If the diff is empty, report "Nothing to review" and stop. State the resolved scope before spawning: "Reviewing branch X vs main — 6 files, 224 insertions."

Phase 2 — Select reviewers

Always include: correctness (code-review), sensitive-data scan (safe-repo, diff-only), and test effectiveness. Add the rest from the diff. Default to ~3–5 reviewers total; honor an explicit count from $ARGUMENTS (2–5).

Reviewer When Kind Suggested agent type
Correctness & bugs (code-review) always audit skill general-purpose (runs code-review)
Sensitive data (safe-repo diff-only) always audit skill general-purpose
Test effectiveness always lens test-auditor
Accessibility (a11y-audit) JSX/TSX/HTML/CSS changed audit skill frontend-architect (or general-purpose)
User-facing strings (i18n) new JSX text nodes / template literals in changed .jsx/.tsx audit skill frontend-architect (or general-purpose)
Bundle / perf (perf-audit) package.json, vite/webpack/next.config.* changed audit skill general-purpose
Dependencies (deps-audit) package.json / lockfile changed audit skill general-purpose
Security & trust boundaries (harden) routes/, api/, controllers/, models/, *.sql, auth/input/external calls audit skill security-auditor
Type safety heavy TS / type-level changes lens general-purpose
Architecture friction cross-module / structural changes lens frontend-architect

Read the full file on GitHub · 128 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 128 lines · 117 tokens per session scan A 024161ccc31b

Subscribe to this mod's changes

review is a skill published in the GitHub repository helderberto/agent-skills (14 stars, last pushed 4d ago), licensed MIT. It adds 117 tokens to every session and 1,909 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

case-interview-practice

Interactive consulting case interview practice with structured frameworks, feedback mechanisms, and progressive difficulty. Use when preparing for management consulting interviews, case competitions, or business problem-solving exercises.

travisjneuman/.claude · 39 tokens

finance

Financial analysis expertise for financial modeling (DCF, LBO, M&A), valuation, financial statement analysis, capital allocation, treasury management, and corporate finance decisions. Use when building financial models, analyzing statements, or making investment decisions.

travisjneuman/.claude · 48 tokens

i18n-localization

Internationalization and localization for global applications. Use when adding multi-language support, handling regional formats, or preparing apps for global markets.

travisjneuman/.claude · 32 tokens

content-repurposer

Adapt content across platforms with tone/format shifting — blog to social, long to short, text to visual outline. Use when repurposing content for different channels, audiences, or formats.

travisjneuman/.claude · 43 tokens

impact-report-writer

Nonprofit/NGO impact report generation with data visualization suggestions, outcome metrics, narrative structure, and program data presentation. Use when writing impact reports, annual reports, or program evaluation summaries.

travisjneuman/.claude · 43 tokens

investment-memo-generator

Investment memo creation combining financial analysis, document generation, and structured templates. Use when creating investment memos, pitch decks, deal summaries, or investment committee materials.

travisjneuman/.claude · 37 tokens